Faire
AI / ML EngineerStrategicAug 6, 2026

Investigate unresolved natural-language discovery sessions

Natural-language requests often carry more buying intent than a keyword system can represent.

Interpreting nuance can improve discovery, while premature certainty can make the experience less trustworthy.

I can describe the feeling I need, but I don’t know which filter is supposed to mean that.

Thin Nguyen · Owner, Modern General Store

A retailer looking for products that match a specific store identity rather than a single category.

What pulls against what

  • expressive intent vs. measurable labels
  • assistant fluency vs. grounded meaning
  • fast prototype vs. correct problem
  • retailer nuance vs. scalable evaluation

What is at stake

The signal suggests a real discovery gap, but not yet the right product or model intervention. The work is choosing what to learn first

Why Faire

Retailers often use wholesale discovery to express an assortment point of view that is difficult to reduce to filters alone.

Written for

LLM application engineerSearch relevance scientistProduct-minded ML engineer

This is the setup. The work is inside.

Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.